ScheduleDAGInstrs: Bug fix for missed memory dependency.

Summary:
In buildSchedGraph(), when adding memory dependencies for loads, move
the call to adjustChainDeps() after the call to
addChainDependency(AliasChain) to handle the case where
addChainDependency(AliasChain) ends up not adding a dependency and
instead putting the SU on the RejectMemNodes list.  The call to
adjustChainDeps() must be done after the call to addChainDependency() in
order to process the SU added to the RejectMemNodes list to create
memory dependencies for it.

Reviewers: hfinkel, atrick, jonpa, resistor

Subscribers: mcrosier, llvm-commits

Differential Revision: http://reviews.llvm.org/D15927

llvm-svn: 256950

2 files changed, 34 insertions, 3 deletions

diff --git a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
index fb82ab7a555..ea2361bfcb3 100644
--- a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
+++ b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
@@ -1005,6 +1005,9 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
           addChainDependency(AAForDep, MFI, MF.getDataLayout(), SU,
                              I->second[i], RejectMemNodes, TrueMemOrderLatency);
       }
+      // This call must come after calls to addChainDependency() since it
+      // consumes the 'RejectMemNodes' list that addChainDependency() possibly
+      // adds to.
       adjustChainDeps(AA, MFI, MF.getDataLayout(), SU, &ExitSU, RejectMemNodes,
                       TrueMemOrderLatency);
       PendingLoads.clear();
@@ -1086,6 +1089,9 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
           addChainDependency(AAForDep, MFI, MF.getDataLayout(), SU, AliasChain,
                              RejectMemNodes);
       }
+      // This call must come after calls to addChainDependency() since it
+      // consumes the 'RejectMemNodes' list that addChainDependency() possibly
+      // adds to.
       adjustChainDeps(AA, MFI, MF.getDataLayout(), SU, &ExitSU, RejectMemNodes,
                       TrueMemOrderLatency);
     } else if (MI->mayLoad()) {
@@ -1133,13 +1139,16 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
           else
             NonAliasMemUses[V].push_back(SU);
         }
-        if (MayAlias)
-          adjustChainDeps(AA, MFI, MF.getDataLayout(), SU, &ExitSU,
-                          RejectMemNodes, /*Latency=*/0);
         // Add dependencies on alias and barrier chains, if needed.
         if (MayAlias && AliasChain)
           addChainDependency(AAForDep, MFI, MF.getDataLayout(), SU, AliasChain,
                              RejectMemNodes);
+        if (MayAlias)
+          // This call must come after calls to addChainDependency() since it
+          // consumes the 'RejectMemNodes' list that addChainDependency()
+          // possibly adds to.
+          adjustChainDeps(AA, MFI, MF.getDataLayout(), SU, &ExitSU,
+                          RejectMemNodes, /*Latency=*/0);
         if (BarrierChain)
           BarrierChain->addPred(SDep(SU, SDep::Barrier));
       }
diff --git a/llvm/test/CodeGen/AArch64/arm64-misched-memdep-bug.ll b/llvm/test/CodeGen/AArch64/arm64-misched-memdep-bug.ll
new file mode 100644
index 00000000000..770521b7528
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/arm64-misched-memdep-bug.ll
@@ -0,0 +1,22 @@
+; REQUIRES: asserts
+; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a57 -enable-misched -verify-misched -debug-only=misched -o - 2>&1 > /dev/null | FileCheck %s
+;
+; Test for bug in misched memory dependency calculation.
+;
+; CHECK: ********** MI Scheduling **********
+; CHECK: misched_bug:BB#0 entry
+; CHECK: SU(2):   %vreg2<def> = LDRWui %vreg0, 1; mem:LD4[%ptr1_plus1] GPR32:%vreg2 GPR64common:%vreg0
+; CHECK:   Successors:
+; CHECK-NEXT:    val SU(5): Latency=4 Reg=%vreg2
+; CHECK-NEXT:    ch  SU(4): Latency=0
+; CHECK: SU(4):   STRWui %WZR, %vreg1, 0; mem:ST4[%ptr2] GPR64common:%vreg1
+; CHECK: SU(5):   %W0<def> = COPY %vreg2; GPR32:%vreg2
+; CHECK: ** ScheduleDAGMI::schedule picking next node
+define i32 @misched_bug(i32* %ptr1, i32* %ptr2) {
+entry:
+  %ptr1_plus1 = getelementptr inbounds i32, i32* %ptr1, i64 1
+  %val1 = load i32, i32* %ptr1_plus1, align 4
+  store i32 0, i32* %ptr1, align 4
+  store i32 0, i32* %ptr2, align 4
+  ret i32 %val1
+}